90fe40b221
debug for fastchat_openai_llm
2023-07-19 10:00:23 +08:00
7dc44249eb
update model_config.py
2023-07-17 21:49:05 +08:00
6f967a069d
udpate
2023-07-17 15:07:52 +08:00
c5026fb4e7
参数校验
2023-07-16 02:19:34 +08:00
22d08f5ec5
必要参数校验
2023-07-16 02:17:52 +08:00
57cb6b05de
add moss-int4
2023-07-13 22:21:00 +08:00
43d1bf4fb3
支持命令行输入ptuning路径
2023-07-13 22:10:54 +08:00
f68d347c25
add ptuning-v2 dir
2023-07-13 21:22:35 +08:00
c5bc21781c
修改模型生成的调用方式，兼容Chain调用
...
修改模型切换的bug
2023-07-12 23:09:28 +08:00
ca13ab8173
测试OPENAI接口成功 ( #813 )
2023-07-11 23:40:49 +08:00
1940da0adf
测试openai接口成功
2023-07-11 23:35:24 +08:00
3a6a6fa8f6
update model_config.py
2023-07-11 20:19:50 +08:00
7480005822
Merge branch 'master' into dev
2023-07-11 20:18:40 +08:00
a5ca4bf26a
1.增加对llama-cpp模型的支持；2.增加对bloom/chatyuan/baichuan模型的支持；3. 修复多GPU部署的bug;4. 修复了moss_llm.py的bug；5. 增加对openai支持（没有api,未测试);6. 支持在多卡情况自定义设备GPU ( #664 )
...
* 修复 bing_search.py的typo;更新model_config.py中Bing Subscription Key申请方式及注意事项
* 更新FAQ，增加了[Errno 110] Connection timed out的原因与解决方案
* 修改loader.py中load_in_8bit失败的原因和详细解决方案
* update loader.py
* stream_chat_bing
* 修改stream_chat的接口，在请求体中选择knowledge_base_id;增加stream_chat_bing接口
* 优化cli_demo.py的逻辑：支持 输入提示；多输入；重新输入
* update cli_demo.py
* add bloom-3b,bloom-7b1,ggml-vicuna-13b-1.1
* 1.增加对llama-cpp模型的支持；2.增加对bloom模型的支持；3. 修复多GPU部署的bug;4. 增加对openai支持（没有api,未测试)；5.增加了llama-cpp模型部署的说明
* llama模型兼容性说明
* modified: ../configs/model_config.py
modified: ../docs/INSTALL.md
在install.md里增加对llama-cpp模型调用的说明
* 修改llama_llm.py以适应llama-cpp模型
* 完成llama-cpp模型的支持；
* make fastchat and openapi compatiable
* 1. 修复/增加对chatyuan,bloom,baichuan-7等模型的支持；2. 修复了moss_llm.py的bug;
* set default model be chatglm-6b
* 在多卡情况下也支持自定义GPU设备
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-07-11 19:36:50 +08:00
7217e3391d
Update model_config.py ( #768 )
...
添加ChatGLM2-6b-int4和ChatGLM2-6b-int8
2023-07-04 19:04:57 +08:00
eaf46a04e3
Add chatglm2-6b configs
2023-06-25 17:04:16 +08:00
017b34647e
update requirements.txt and model_config.py
2023-06-18 21:52:56 +08:00
25b46a7b9e
标题增强 ( #631 )
...
* Add files via upload
* Update local_doc_qa.py
* Update model_config.py
* Update zh_title_enhance.py
* Add files via upload
* Update README.md
* fix bugs in MyFAISS.delete_doc
* fix:前端知识库获取失败.
* update zh_title_enhance.py
* update zh_title_enhance.py
* Update zh_title_enhance.py
* add test/textsplitter
* add test_zh_title_enhance.py
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
Co-authored-by: JZF <jiangzhifeng_jzf@163.com>
Co-authored-by: fxjhello <127916299+fxjhello@users.noreply.github.com>
2023-06-18 21:45:06 +08:00
a70df98825
更新FAQ,model_config.py,bing_search.py文件，增加bing搜索问答相关问题的原因和可能解决方案，修复了一些typo;修改loader.py中load_in_8bit失败的原因和详细解决方案 ( #610 )
...
* 修复 bing_search.py的typo;更新model_config.py中Bing Subscription Key申请方式及注意事项
* 更新FAQ，增加了[Errno 110] Connection timed out的原因与解决方案
* 修改loader.py中load_in_8bit失败的原因和详细解决方案
* update loader.py
2023-06-14 21:31:26 +08:00
a887df1715
add knowledge_base folder and move vector_store and content inside
2023-06-13 23:54:29 +08:00
0abd2d9992
llama_llm.py 提示词修改
2023-06-13 18:36:07 +08:00
ecd7b6133b
updata model_config.py
2023-06-12 00:10:47 +08:00
66c4e9de92
Merge branch 'master' into dev
2023-06-11 21:16:08 +08:00
5afee735a9
bing搜索agent
2023-06-10 22:15:39 +08:00
dec0c46816
add support for new embedding models: moka-ai/m3e-base and moka-ai/m3e-small
2023-06-09 19:04:34 +08:00
218aca2e20
删除model_dir和NO_REMOTE_MODEL
2023-06-08 16:51:04 +08:00
20f1daff1a
add fastchat.md
2023-05-31 22:50:35 +08:00
ab73f6ad93
适配远程LLM调用
2023-05-31 22:26:39 +08:00
24324563d6
适配远程LLM调用
2023-05-31 22:11:28 +08:00
0f2ea29194
调整项目结构,适配远程LLM调用生成问题。新增fastchat_openai_llm.py实现fastchat openai报文报文形式调用
2023-05-31 00:00:35 +08:00
88fee48d8c
use lru_cache to optimize loading of local vector store ( #496 )
...
* Add files via upload
* Update README.md
* use lru_cache to optimize loading of local vector store
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
Co-authored-by: liunux <liunux@office>
2023-05-30 23:05:39 +08:00
a1b1b78108
使用model_config默认配置启动
...
llama_llm.py 删除流式输出
base.py、shared.py 删除多余代码
fastchat_llm.py 业务实现
2023-05-23 23:10:31 +08:00
d2983e935f
update loaders
2023-05-22 00:15:29 +08:00
483b7dd291
update model_config.py
2023-05-21 22:41:22 +08:00
67e26fe730
update model_config.py
2023-05-21 22:30:28 +08:00
49e47231af
update model_config.py
2023-05-19 23:16:39 +08:00
7d837078e7
update model_config.py
2023-05-19 23:12:39 +08:00
75cf9f9b4e
ptuning-v2配置
2023-05-18 23:19:23 +08:00
33bbb4779e
llm_model_dict 处理了loader的一些预设行为，如加载位置，模型名称，模型处理器实例, 定义checkpoint名称和远程路径
...
loader.py: 模型重载
定义 generatorAnswer 增加 AnswerResultStream
定义generate_with_callback收集器，在每次响应时将队列数据同步到AnswerResult
requirements.txt 变更项目依赖
2023-05-18 22:54:41 +08:00
64406cee45
Add MOSS ( #317 )
...
* Add MOSS
* Update local_doc_qa.py
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-05-11 18:42:19 +08:00
2987c9cd52
增加允许跨域调用API功能 ( #279 )
2023-05-11 09:32:58 +08:00
f403ad755c
update README.md
2023-05-11 00:09:38 +08:00
264981e4b6
update webui.py
2023-05-10 23:21:36 +08:00
55504fcd4d
新增加知识库测试能力 ( #302 )
2023-05-10 17:18:20 +08:00
47e9bdb122
logging: 格式日志输出 ( #268 )
...
* logging: 统一日志格式输出
---------
Co-authored-by: Bob Chang <bob.chang@amway.com>
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-05-08 18:29:09 +08:00
e2d7452c7b
update chinese_text_splitter.py
2023-05-06 23:26:49 +08:00
7497b261b3
完善知识库路径问题，完善api接口 ( #245 )
...
* Fix 知识库无法上载,NLTK_DATA_PATH路径错误 (#236 )
* Update chatglm_llm.py (#242 )
* 完善知识库路径问题，完善api接口
统一webui、API接口知识库路径，后续路径如下：
知识库路经就是：/项目代码文件夹/vector_store/'知识库名字'
文件存放路经：/项目代码文件夹/content/'知识库名字'
修复通过api接口创建知识库的BUG，完善API接口功能。
* Update model_config.py
---------
Co-authored-by: Bob Chang <bob-chang@outlook.com>
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-05-05 18:44:37 +08:00
14d998b8e6
可选择lora权重加载 ( #231 )
...
* Add files via upload
增加lora权重使用
* Update model_config.py
* Add files via upload
修复一个小错误，少写了模型加载
* 使用lora微调的权重
使用lora微调的权重
* Update model_config.py
2023-05-04 21:01:55 +08:00
07ff81a119
update torch_gc
2023-05-04 20:48:36 +08:00
2c1fd2bdd5
add api.py
2023-05-03 22:31:28 +08:00
e0cf26019b
Use fastapi to implement API ( #209 )
...
* Use fastapi to implement API
* Update model_config.py
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-05-03 21:29:28 +08:00
c98c4888e9
update PROMPT_TEMPLATE
2023-05-02 00:28:09 +08:00
7a406e4263
Dev ( #214 )
...
* github: Add issue templates
* supports GPU usage in docker (#197 )
* 上下文的prompt模版内容修改
---------
Co-authored-by: Calcitem <calcitem@outlook.com>
Co-authored-by: cocomany <124849750+cocomany@users.noreply.github.com>
Co-authored-by: glide-the <2533736852@qq.com>
2023-05-01 23:55:37 +08:00
0e8cc0d16c
add streaming option in configs/model_config.py
2023-05-01 23:52:28 +08:00
98a8281b29
update text_splitter
2023-04-28 00:02:42 +08:00
cae2427e1e
add llm model and embedding model options in model_config.py
2023-04-27 07:48:43 +08:00
4dc762849b
update model_config.py
2023-04-27 07:40:57 +08:00
c620ab0d6c
update model_config.py
2023-04-26 23:27:15 +08:00
b3f83060c8
update model_config.py
2023-04-26 23:27:15 +08:00
b48e399e9e
Update model_config.py
2023-04-21 21:27:20 +08:00
37ceeae6e2
提交更
2023-04-21 21:27:20 +08:00
13b41553a3
update project to v0.1.3
2023-04-19 23:02:47 +08:00
811d5a2e46
Update model_config.py
2023-04-18 19:45:50 +08:00
3eaa25c9ba
feat: add api for knowledge_based QA
2023-04-18 10:08:13 +08:00
2cd52f6605
Support p-tuning-v2
2023-04-15 14:43:12 +08:00
eabef0415b
update cli_demo.py
2023-04-13 23:20:45 +08:00
a6184b01be
修改项目架构
2023-04-13 23:01:52 +08:00
hzg0601
imClumsyPanda
glide-the
zg h
stc2001
kiddog99
liunux4odoo
Tyler Luan
akou
shrimp
CHANGXUBO
Bing Han
soon
wangxinkai
Thaumstrial